I'm a Senior AI/ML Engineer with over 10 years of software engineering experience building production applications, AI-powered systems, and scalable data platforms. My background combines applied AI, backend development, and cloud infrastructure, with a strong focus on making AI applications reliable, secure, and useful in real-world environments.
Most recently, at Tempus Labs, I developed AI-assisted research applications using Python, FastAPI, LLM APIs, retrieval-augmented generation (RAG), and PostgreSQL/pgvector. I helped improve grounded citation pass rates from 71.2% to 93.2% across a fixed 250-question evaluation benchmark. I also developed model-facing APIs with structured output validation, source attribution, automated evaluation, and reliable error-handling workflows.
Beyond generative AI, I've worked extensively with machine learning integration, data engineering, and production infrastructure. At Tempus, I helped improve clinical metadata services processing approximately 2.4 million records monthly and optimize PySpark and Apache Airflow pipelines, reducing batch processing time by 39%. Earlier in my career, I worked on CI/CD automation and platform engineering at Jellyvision, as well as full-stack application development at Select Rehab.
I'm particularly interested in opportunities involving LLM applications, RAG systems, MLOps, AI platform engineering, and scalable backend services. I enjoy solving challenging engineering problems, collaborating with cross-functional teams, and building dependable software that delivers measurable value.
